基于自适应背景模型的动态场景目标检测

背景建模一直是运动目标检测中的一个重要课题。该文提出一个适用于动态背景的基于非参数估计的前景背景对比模型。模型通过核函数估计的方法模拟了像素点五维特征向量的概率分布,并在图像序列中滚动更新。实验证明,上述算法能够在一般目标检测,特别是动态场景(摇动树枝等)的检测中取得较好的效果。

Object Detection in Nonstationary Scenes Based on Adaptive Background Models

Background modeling is an important issue in accurate detection of moving objects. This paper presents a novel non - parametric- foreground - background model which explores the complex temporal and spatial dependencies in nonstationary scenes. The model estimates theprobability of observing pixels＇ five-dimensioned feature vector which represents its intensity values and spatial position information. The model isbuih and rolling-updated by kernel density estimation. Extensive experiments with nonstationary scenes demonstrate the utility and- performance of the proposed approach.